INDEX

Explanations

technical terms and identifiers related to policies or regulations

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 oprot

-0.78

NameInMap

-0.76

expandindo

-0.75

+#+#

-0.74

 NavController

-0.71

脚注の使い方

-0.70

 Italijani

-0.67

Personensuche

-0.65

 sympy

-0.65

makeConstraints

-0.64

POSITIVE LOGITS

 initComponents

0.51

 platform

0.45

ㅐ

0.44

ReusableCell

0.41

 Platform

0.40

wki

0.40

 seuls

0.39

oy

0.39

ühungen

0.37

Rad

0.37

Activations Density 1.452%

technical terms and identifiers related to policies or regulations

No Comments

No Known Activations